© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4646
    Prev
    Next
    INDEX
    Explanations

    mentions of World War II, including dates, countries, and events

    oai_token-act-pair · gemini-2.0-flash

    9

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     مرئيه
    -0.69
    بوابة
    -0.68
    RenderAtEndOf
    -0.62
    setVerticalGroup
    -0.62
    sidemargin
    -0.60
     useAppContext
    -0.58
    usercontent
    -0.58
     виправивши
    -0.58
     Reſ
    -0.58
    DOCTYPE
    -0.57
    POSITIVE LOGITS
    defer
    0.49
    interopRequire
    0.44
    Њ
    0.41
     kính
    0.39
    evich
    0.39
    switch
    0.38
     Regis
    0.38
    quisa
    0.37
     Paglinawan
    0.37
    Idade
    0.37
    Activations Density 0.236%

    No Known Activations